Skip to content
  • Sign In
  • Try Now
View all events
Large Language Models (LLMs)

Choosing the Right LLM

Published by Pearson

Intermediate content levelIntermediate

How to select, train, and apply state-of-the-art LLMs to real-world business use cases

  • This hands-on workshop arms you to solve real business problems
  • Get a comprehensive review of the latest APIs and open-source models
  • Learn how to select models, train them, and apply them to benefit your business

2024 is the year that GenAI gets mainstream acceptance in the workplace. As Data Scientists, Data Engineers, and Software Engineers, we will be counted on to solve business problems taking advantage of the remarkable power of LLMs.

This class is a practical, hands-on workshop to applying LLMs to solve business problems. We start with a whirlwind tour of state-of-the-art models and APIs that are available to us and run experiments to see how they perform with various datasets. We then examine a number of real business scenarios and learn how to select and fine-tune the right model for the problem.

In the final section, we look to the future: with Gemini Ultra, GPT5, and other advances on the horizon, what are the new commercial applications we can envisage for 2024 and beyond, and how can we best prepare ourselves and our business to be at the forefront of this progress?

What you’ll learn and how you can apply it

  • Identify business problems in your organization that are ripe for Gen AI solutions
  • Understand the pros and cons of the state-of-the-art LLM models and APIs
  • Select LLM models and training techniques to optimize your solutions
  • Deliver concrete commercial benefit with LLMs

This live event is for you because...

  • Whether you are a Data Scientist, a Data Engineer, or a Software Developer – if you’re excited about the potential for LLMs to have massive commercial impact, this event will give you the knowledge you need to deliver business value
  • Prior experience with LLMs is helpful but not essential, as this class is practical
  • You will leave this class ready to make an impact in your day job

Prerequisites

  • Basic to intermediate Python programming, and familiarity with a Jupyter Notebook or Lab setup
  • Basic to intermediate experience with LLMs is helpful but not required

Course Set-up

  • Not required, but ideally: access to Jupyter Notebook or Lab, or Google colab account
  • Not required, but ideally: Hugging Face account
  • Jupyter notebooks with curated datasets provided on https://github.com/ed-donner/

Recommended Preparation

Recommended Follow-up

Schedule

The time frames are only estimates and may vary according to how the class is progressing.

Segment 1: The LLM Frontier (60 mins)

  • A Whirlwind Recap
  • From Stochastic Parrot to Emergent Intelligence
  • LLM Cambrian Explosion; Llama 2, the GPT Store, and more
  • Emergence of Co-Pilots, Cyborg vs Centaur
  • Models & Training Techniques, with Hands-On Examples for You to Try
  • The Transformer
  • Fine-tuning, LoRA, QLoRA
  • RAG
  • Latest Advances
  • Mamba architecture
  • Sora, multi-modality
  • Humanoid robotics

Q&A (10 minutes)

Break (10 minutes)

Segment 2: The Model Matchup (60 mins)

  • Setting the Scene
  • The key players
  • How to judge LLMs – benchmarks and their limitations
  • Leaderboards and Arenas
  • Ranking the State-of-the-Art Models
  • Open source
  • Closed source
  • In the Real-World
  • Business applications
  • Use in existing business products
  • The case of the Air Canada customer support agent

Q&A (10 minutes)

Break (10 minutes)

Segment 3: TIME TO CODE! Selecting and Applying LLMs to Solve Real Problems (60 mins)

  • Strategy
  • Applying Our Strategy to 3 Actual Business Problems, Hands-On in Jupyter Notebooks with Curated Datasets
  • Fine-tuning an agent
  • Generating code for your system
  • Solving a specific commercial problem
  • Making Commercial Impact Now and in the Future
  • Preparing for what’s to come in 2024

Q&A (10 minutes)

Course wrap-up and next steps (10 minutes)

Your Instructor

  • Ed Donner

    Ed Donner is a technology leader and repeat founder of AI startups. He’s the co-founder and CTO of Nebula.io, the platform to source, understand, engage and manage talent, using Generative AI and other forms of machine learning. Nebula matches people and roles with greater accuracy and speed than previously imaginable — no keywords required. Nebula’s long-term goal is to help people discover their potential and pursue their reason for being. Previously, Ed was the founder and CEO of AI startup untapt, an Accenture Fintech Innovation Lab company, acquired in 2020. Before that, Ed was a Managing Director at JPMorgan Chase, leading a team of 300 software engineers in Risk Technology across 3 continents, after a 15-year technology career on Wall Street. Ed holds a patent for a Deep Learning matching engine issued in 2023, and an MA in Physics from Oxford.

    linkedinXlinksearch